Towards Event-Aware Forecasting in DeFi: Insights from On-chain Automated Market Maker Protocols

TL;DR

This paper introduces a comprehensive dataset and a novel loss function for event-aware modeling of on-chain AMM protocols in DeFi, significantly improving time prediction accuracy.

Contribution

It provides the first detailed dataset with fine-grained event annotations and proposes an uncertainty-weighted loss function for better event timing predictions in AMMs.

Findings

The dataset contains 8.9 million on-chain event records from four AMM protocols.

The proposed UWM loss reduces time prediction error by an average of 56.41%.

The framework maintains high accuracy in event type classification.

Abstract

Automated Market Makers (AMMs), as a core infrastructure of decentralized finance (DeFi), uniquely drive on-chain asset pricing through a deterministic reserve ratio mechanism. Unlike traditional markets, AMM price dynamics is triggered largely by on-chain events (e.g., swap) that change the reserve ratio, rather than by continuous responses to off-chain information. This makes event-level analysis crucial for understanding price formation mechanisms in AMMs. However, existing research generally neglects the micro-structural dynamics at the AMMs level, lacking both a comprehensive dataset covering multiple protocols with fine-grained event classification and an effective framework for event-aware modeling. To fill this gap, we construct a dataset containing 8.9 million on-chain event records from four representative AMMs protocols: Pendle, Uniswap v3, Aave and Morpho, with precise annotations of transaction type and block height timestamps. Furthermore, we propose an Uncertainty Weighted Mean Squared Error (UWM) loss function, which incorporates the block interval regression term into the traditional Time-Point Process (TPP) objective function by weighting the uncertainty with homoscedasticity. Extensive experiments on eight advanced TPP architectures demonstrate that this loss function reduces the time prediction error by an average of 56.41\% while maintaining the accuracy of event type prediction, establishing a robust benchmark for event-aware prediction in the AMMs ecosystem. This work provides the necessary data foundation and methodological framework for modeling the discreteness and event-driven characteristics of on-chain price discovery. All datasets and source code are publicly available. https://github.com/yosen-king/Deep-AMM-Events